Autoregressive Model

Saw this from the Tesla AI Day.

  • Where?

And it’s a term that seems to pop around. But I think that all it does is really allow you to predict (regress) future data based on past data. So isn’t this just a simple RNN?

They also mention this in the Neural Autoregressive Flow.


Assuming a fully expressive Bayes net structure, any joint distribution can be written as a product of conditionals